def test_ibd_segments_both_parents(self):
'''Test computing GERMLINE IBD segments.'''
h_mat = ig._HapMatrix(self.problem, self.sibs)
m = self.ibd_computer.ibd_segments(h_mat)
assert_segments_almost_equal(m,
[((0 , 344), (16484792, 21449028, 4.964, 0), ((2, 0), (4, 0))),
((0 , 344), (16484792, 21449028, 4.964, 0), ((1, 0), (4, 0))),
((0 , 780), (16484792, 26920270, 10.435, 0), ((4, 1), (2, 1))),
((2145, 2996), (39608193, 48759228, 9.151, 0), ((1, 1), (2, 1))),
((2145, 2996), (39608193, 48759228, 9.151, 0), ((4, 1), (2, 1))),
((885 , 3218), (27425790, 51156933, 23.731, 0), ((4, 1), (1, 1))),
((0 , 3218), (16484792, 51156933, 34.672, 0), ((2, 0), (1, 0)))],
full_data=True, decimal=3, err_msg='Wrong IBD segments, raw')
# A transitive-logic test test to see that we don't miss any intervals with GERMLINE
m.group_to_disjoint(False)
assert_segments_almost_equal(m,
[((0 , 344), (16484792, 21449028, 4.964, 0), ((2, 0), (1, 0), (4, 0))),
((0 , 344), (16484792, 21449028, 4.964, 0), ((4, 1), (2, 1))),
((344 , 780), (21449028, 26920270, 5.471, 0), ((2, 0), (1, 0))),
((344 , 780), (21449028, 26920270, 5.471, 0), ((4, 1), (2, 1))),
((780 , 885), (26920270, 27425790, 0.506, 0), ((2, 0), (1, 0))),
((885 , 2145), (27425790, 39608193, 12.182, 0), ((2, 0), (1, 0))),
((885 , 2145), (27425790, 39608193, 12.182, 0), ((4, 1), (1, 1))),
((2145, 2996), (39608193, 48759228, 9.151, 0), ((4, 1), (1, 1), (2, 1))),
((2145, 2996), (39608193, 48759228, 9.151, 0), ((2, 0), (1, 0))),
((2996, 3218), (48759228, 51156933, 2.398, 0), ((2, 0), (1, 0))),
((2996, 3218), (48759228, 51156933, 2.398, 0), ((4, 1), (1, 1)))],
full_data=True, decimal=3, err_msg='Wrong IBD segments, grouped')
stats = np.array([(len(s.samples), s.length) for s in m])
best_segment = np.lexsort((-stats[:, 1], -stats[:, 0]))[0]
assert_equal(best_segment, 7, 'Wrong best segment (IBD set size + length)')
assert_almost_equal(m[best_segment].length, 9.15, decimal=2, err_msg='Wrong best segment (IBD set size + length)')
assert_equal(m[best_segment].samples, set([(4, 1), (1, 1), (2, 1)]), err_msg='Wrong best segment (IBD set size + length)')
def test_masked_binary_operations2(self):
# Tests domained_masked_binary_operation
(x, mx) = self.data
xmx = masked_array(mx.data.__array__(), mask=mx.mask)
self.assertTrue(isinstance(divide(mx, mx), mmatrix))
self.assertTrue(isinstance(divide(mx, x), mmatrix))
assert_equal(divide(mx, mx), divide(xmx, xmx))
def test_fancy_dtype_alt(self):
"Check that a nested dtype isn't MIA"
data = StringIO('1,2,3.0\n4,5,6.0\n')
fancydtype = np.dtype([('x', int), ('y', [('t', int), ('s', float)])])
test = np.mafromtxt(data, dtype=fancydtype, delimiter=',')
control = ma.array([(1, (2, 3.0)), (4, (5, 6.0))], dtype=fancydtype)
assert_equal(test, control)
def test_with_masked_column_uniform(self):
"Test masked column"
data = StringIO('1 2 3\n4 5 6\n')
test = np.genfromtxt(data, dtype=None,
missing_values='2,5', usemask=True)
control = ma.array([[1, 2, 3], [4, 5, 6]], mask=[[0, 1, 0], [0, 1, 0]])
assert_equal(test, control)
def test_out(self):
x = masked_array(np.arange(30).reshape(10, 3))
x[:3] = x[-3:] = masked
out = masked_array(np.ones(10))
r = median(x, axis=1, out=out)
assert_equal(r, out)
assert_(type(r) == MaskedArray)
def test_2D(self):
x = ma.array([[1, 1, 1],
[1, 1, 1],
[4, 4, 3],
[1, 1, 1],
[1, 1, 1]])
assert_equal(mstats.scoreatpercentile(x,50), [1,1,1])
def test_different_field_order(self):
# gh-8940
a = np.zeros(3, dtype=[('a', 'i4'), ('b', 'f4'), ('c', 'u1')])
b = np.ones(3, dtype=[('c', 'u1'), ('b', 'f4'), ('a', 'i4')])
# this should not give a FutureWarning:
j = join_by(['c', 'b'], a, b, jointype='inner', usemask=False)
assert_equal(j.dtype.names, ['b', 'c', 'a1', 'a2'])
def test_intersect1d(self):
# Test intersect1d
x = array([1, 3, 3, 3], mask=[0, 0, 0, 1])
y = array([3, 1, 1, 1], mask=[0, 0, 0, 1])
test = intersect1d(x, y)
control = array([1, 3, -1], mask=[0, 0, 1])
assert_equal(test, control)
def test_unnamed_and_named_fields(self):
# Test combination of arrays w/ & w/o named fields
(_, x, _, z) = self.data
test = stack_arrays((x, z))
control = ma.array([(1, -1, -1), (2, -1, -1),
(-1, 'A', 1), (-1, 'B', 2)],
mask=[(0, 1, 1), (0, 1, 1),
(1, 0, 0), (1, 0, 0)],
dtype=[('f0', int), ('A', '|S3'), ('B', float)])
assert_equal(test, control)
assert_equal(test.mask, control.mask)
test = stack_arrays((z, x))
control = ma.array([('A', 1, -1), ('B', 2, -1),
(-1, -1, 1), (-1, -1, 2), ],
mask=[(0, 0, 1), (0, 0, 1),
(1, 1, 0), (1, 1, 0)],
dtype=[('A', '|S3'), ('B', float), ('f2', int)])
assert_equal(test, control)
assert_equal(test.mask, control.mask)
test = stack_arrays((z, z, x))
control = ma.array([('A', 1, -1), ('B', 2, -1),
('A', 1, -1), ('B', 2, -1),
(-1, -1, 1), (-1, -1, 2), ],
mask=[(0, 0, 1), (0, 0, 1),
(0, 0, 1), (0, 0, 1),
(1, 1, 0), (1, 1, 0)],
dtype=[('A', '|S3'), ('B', float), ('f2', int)])
assert_equal(test, control)
def test_outer_join(self):
a, b = self.a, self.b
test = join_by(('a', 'b'), a, b, 'outer')
control = ma.array([(0, 50, 100, -1), (1, 51, 101, -1),
(2, 52, 102, -1), (3, 53, 103, -1),
(4, 54, 104, -1), (5, 55, 105, -1),
(5, 65, -1, 100), (6, 56, 106, -1),
(6, 66, -1, 101), (7, 57, 107, -1),
(7, 67, -1, 102), (8, 58, 108, -1),
(8, 68, -1, 103), (9, 59, 109, -1),
(9, 69, -1, 104), (10, 70, -1, 105),
(11, 71, -1, 106), (12, 72, -1, 107),
(13, 73, -1, 108), (14, 74, -1, 109)],
mask=[(0, 0, 0, 1), (0, 0, 0, 1),
(0, 0, 0, 1), (0, 0, 0, 1),
(0, 0, 0, 1), (0, 0, 0, 1),
(0, 0, 1, 0), (0, 0, 0, 1),
(0, 0, 1, 0), (0, 0, 0, 1),
(0, 0, 1, 0), (0, 0, 0, 1),
(0, 0, 1, 0), (0, 0, 0, 1),
(0, 0, 1, 0), (0, 0, 1, 0),
(0, 0, 1, 0), (0, 0, 1, 0),
(0, 0, 1, 0), (0, 0, 1, 0)],
dtype=[('a', int), ('b', int),
('c', int), ('d', int)])
assert_equal(test, control)
def test_addfield(self):
# Tests addfield
(mrec, nrec, ddtype) = self.data
(d, m) = ([100, 200, 300], [1, 0, 0])
mrec = addfield(mrec, ma.array(d, mask=m))
assert_equal(mrec.f3, d)
assert_equal(mrec.f3._mask, m)
def test_pickling_subbaseclass(self):
# Test pickling w/ a subclass of ndarray
a = masked_array(np.matrix(list(range(10))), mask=[1, 0, 1, 0, 0] * 2)
a_pickled = pickle.loads(a.dumps())
assert_equal(a_pickled._mask, a._mask)
assert_equal(a_pickled, a)
assert_(isinstance(a_pickled._data, np.matrix))
def test_view_simple_dtype(self):
(mrec, a, b, arr) = self.data
ntype = (np.float, 2)
test = mrec.view(ntype)
self.assertTrue(isinstance(test, ma.MaskedArray))
assert_equal(test, np.array(list(zip(a, b)), dtype=np.float))
self.assertTrue(test[3, 1] is ma.masked)
def test_fromrecords(self):
# Test construction from records.
(mrec, nrec, ddtype) = self.data
#......
palist = [(1, 'abc', 3.7000002861022949, 0),
(2, 'xy', 6.6999998092651367, 1),
(0, ' ', 0.40000000596046448, 0)]
pa = recfromrecords(palist, names='c1, c2, c3, c4')
mpa = fromrecords(palist, names='c1, c2, c3, c4')
assert_equal_records(pa, mpa)
#.....
_mrec = fromrecords(nrec)
assert_equal(_mrec.dtype, mrec.dtype)
for field in _mrec.dtype.names:
assert_equal(getattr(_mrec, field), getattr(mrec._data, field))
_mrec = fromrecords(nrec.tolist(), names='c1,c2,c3')
assert_equal(_mrec.dtype, [('c1', int), ('c2', float), ('c3', '|S5')])
for (f, n) in zip(('c1', 'c2', 'c3'), ('a', 'b', 'c')):
assert_equal(getattr(_mrec, f), getattr(mrec._data, n))
_mrec = fromrecords(mrec)
assert_equal(_mrec.dtype, mrec.dtype)
assert_equal_records(_mrec._data, mrec.filled())
assert_equal_records(_mrec._mask, mrec._mask)
def test_two_keys_two_vars(self):
a = np.array(
list(zip(np.tile([10, 11], 5), np.repeat(np.arange(5), 2), np.arange(50, 60), np.arange(10, 20))),
dtype=[("k", int), ("a", int), ("b", int), ("c", int)],
)
b = np.array(
list(zip(np.tile([10, 11], 5), np.repeat(np.arange(5), 2), np.arange(65, 75), np.arange(0, 10))),
dtype=[("k", int), ("a", int), ("b", int), ("c", int)],
)
control = np.array(
[
(10, 0, 50, 65, 10, 0),
(11, 0, 51, 66, 11, 1),
(10, 1, 52, 67, 12, 2),
(11, 1, 53, 68, 13, 3),
(10, 2, 54, 69, 14, 4),
(11, 2, 55, 70, 15, 5),
(10, 3, 56, 71, 16, 6),
(11, 3, 57, 72, 17, 7),
(10, 4, 58, 73, 18, 8),
(11, 4, 59, 74, 19, 9),
],
dtype=[("k", int), ("a", int), ("b1", int), ("b2", int), ("c1", int), ("c2", int)],
)
test = join_by(["a", "k"], a, b, r1postfix="1", r2postfix="2", jointype="inner")
assert_equal(test.dtype, control.dtype)
assert_equal(test, control)
def test_skewtest_2D_notmasked(self):
# a normal ndarray is passed to the masked function
x = np.random.random((20,2))*20.
r = stats.skewtest(x)
rm = stats.mstats.skewtest(x)
assert_equal(r[0][0],rm[0][0])
assert_equal(r[0][1],rm[0][1])
def test_unnamed_and_named_fields(self):
# Test combination of arrays w/ & w/o named fields
(_, x, _, z) = self.data
test = stack_arrays((x, z))
control = ma.array(
[(1, -1, -1), (2, -1, -1), (-1, "A", 1), (-1, "B", 2)],
mask=[(0, 1, 1), (0, 1, 1), (1, 0, 0), (1, 0, 0)],
dtype=[("f0", int), ("A", "|S3"), ("B", float)],
)
assert_equal(test, control)
assert_equal(test.mask, control.mask)
test = stack_arrays((z, x))
control = ma.array(
[("A", 1, -1), ("B", 2, -1), (-1, -1, 1), (-1, -1, 2)],
mask=[(0, 0, 1), (0, 0, 1), (1, 1, 0), (1, 1, 0)],
dtype=[("A", "|S3"), ("B", float), ("f2", int)],
)
assert_equal(test, control)
assert_equal(test.mask, control.mask)
test = stack_arrays((z, z, x))
control = ma.array(
[("A", 1, -1), ("B", 2, -1), ("A", 1, -1), ("B", 2, -1), (-1, -1, 1), (-1, -1, 2)],
mask=[(0, 0, 1), (0, 0, 1), (0, 0, 1), (0, 0, 1), (1, 1, 0), (1, 1, 0)],
dtype=[("A", "|S3"), ("B", float), ("f2", int)],
)
assert_equal(test, control)
def test_leftouter_join(self):
a, b = self.a, self.b
test = join_by(("a", "b"), a, b, "leftouter")
control = ma.array(
[
(0, 50, 100, -1),
(1, 51, 101, -1),
(2, 52, 102, -1),
(3, 53, 103, -1),
(4, 54, 104, -1),
(5, 55, 105, -1),
(6, 56, 106, -1),
(7, 57, 107, -1),
(8, 58, 108, -1),
(9, 59, 109, -1),
],
mask=[
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
(0, 0, 0, 1),
],
dtype=[("a", int), ("b", int), ("c", int), ("d", int)],
)
assert_equal(test, control)
def test_simple_flexible(self):
# Test recursive_fill_fields on flexible-array
a = np.array([(1, 10.0), (2, 20.0)], dtype=[("A", int), ("B", float)])
b = np.zeros((3,), dtype=a.dtype)
test = recursive_fill_fields(a, b)
control = np.array([(1, 10.0), (2, 20.0), (0, 0.0)], dtype=[("A", int), ("B", float)])
assert_equal(test, control)
def test_w_singlefield(self):
# Test single field
test = merge_arrays((np.array([1, 2]).view([("a", int)]), np.array([10.0, 20.0, 30.0])))
control = ma.array(
[(1, 10.0), (2, 20.0), (-1, 30.0)], mask=[(0, 0), (0, 0), (1, 0)], dtype=[("a", int), ("f1", float)]
)
assert_equal(test, control)
def test_tabulate1D(self):
"Tests the transformation from a 1D MaskedArray to..."
# Test 1D
data1D = self.data['data1D']
_data1D = tabulate(data1D)
assert_equal(_data1D['_data'], data1D.filled())
assert_equal(_data1D['_mask'], data1D.mask)
def test_clump_unmasked(self):
# Test clump_unmasked
a = masked_array(np.arange(10))
a[[0, 1, 2, 6, 8, 9]] = masked
test = clump_unmasked(a)
control = [slice(3, 6), slice(7, 8), ]
assert_equal(test, control)
def _test_complete_genotype_partial(self, h, h_expected):
"""Test completing a haplotype with one known entry vs. a partially-called genotype. Comprehensive
checks for a single h and all possible genotypes g."""
g = np.array(list(it.product(xrange(3), xrange(3))))
h_temp = np.tile(h, (9, 1)).copy()
gt.complete_haplotype_partial(h_temp, g)
assert_equal(h_temp, h_expected, "Unexpected haplotype completion")
def test_convert_to_annual(self):
"Test convert_to_annual"
base = dict(D=1, H=24, T=24 * 60, S=24 * 3600)
#for fq in ('D', 'H', 'T', 'S'):
# Don't test for minuTe and Second frequency, too time consuming.
for fq in ('D', 'H'):
dates = date_array(start_date=Date(fq, '2001-01-01 00:00:00'),
end_date=Date(fq, '2004-12-31 23:59:59'))
bq = base[fq]
series = time_series(range(365 * bq) * 3 + range(366 * bq),
dates=dates)
control = ma.masked_all((4, 366 * bq), dtype=series.dtype)
control[0, :58 * bq] = range(58 * bq)
control[0, 59 * bq:] = range(58 * bq, 365 * bq)
control[[1, 2]] = control[0]
control[3] = range(366 * bq)
test = convert_to_annual(series)
assert_equal(test, control)
#
series = time_series(range(59, 365) + range(366) + range(365),
start_date=Date('D', '2003-03-01'))
test = convert_to_annual(series)
assert_equal(test[:, 59:62],
ma.masked_values([[-1, 59, 60], [59, 60, 61], [-1, 59, 60]],
- 1))
def test_guessfreq(self):
"Test the guessing of frequency."
dates = [
(_c.FR_MIN,
['2001-01-01 00:00', '2001-01-01 00:30', '2001-01-01 01:00']),
(_c.FR_MIN,
['2001-01-01 00:00', '2001-01-01 01:30', '2001-01-01 03:00']),
(_c.FR_HR,
['2001-01-01 00:00', '2001-01-01 01:00', '2001-01-01 03:00']),
(_c.FR_HR,
['2001-01-01 00:00', '2001-01-01 01:00', '2002-01-01 03:00']),
(_c.FR_DAY,
['1959-01-01', '2009-07-31', '2009-08-01', '2009-08-02']),
(_c.FR_BUS,
['2001-07-31', '2009-08-03', '2009-08-04']),
(_c.FR_MTH,
['2001-01-01', '2001-02-01', '2002-03-01']),
(_c.FR_MTH,
['2001-01-01', '2001-04-01', '2002-03-01']),
(_c.FR_QTR,
['2004-01-01', '2004-04-01', '2005-01-01']),
(_c.FR_WKTHU,
['2004-01-01', '2004-01-22', '2004-12-30']),
]
for fr, dt in dates:
assert_equal(guess_freq(dt), fr)
def test_ibs_segments(self):
'''Test computing GERMLINE IBD segments.'''
m = ig.ibd_germline(self.problem, self.sibs)
assert_equal(m.length, 24, 'Wrong # IBD grouped segments')
assert_segments_almost_equal(m,
[((1 , 434), (17065079, 23614026, 6.549, 0), ((0, 1), (3, 1), (4, 1), (1, 1))),
((1 , 434), (17065079, 23614026, 6.549, 0), ((5, 1), (0, 0), (4, 0))),
((1 , 434), (17065079, 23614026, 6.549, 0), ((3, 0), (1, 0))),
((434 , 537), (23614026, 24732045, 1.118, 0), ((0, 1), (3, 1), (4, 1))),
((434 , 537), (23614026, 24732045, 1.118, 0), ((5, 1), (0, 0), (4, 0))),
((537 , 848), (24732045, 27321172, 2.589, 0), ((3, 0), (5, 1), (0, 0), (4, 0))),
((537 , 848), (24732045, 27321172, 2.589, 0), ((0, 1), (3, 1), (4, 1))),
((537 , 848), (24732045, 27321172, 2.589, 0), ((1, 1), (5, 0))),
((848 , 948), (27321172, 27671082, 0.350, 0), ((0, 1), (3, 1), (4, 1))),
((848 , 948), (27321172, 27671082, 0.350, 0), ((3, 0), (5, 1), (0, 0))),
((848 , 948), (27321172, 27671082, 0.350, 0), ((1, 1), (5, 0))),
((948 , 2481), (27671082, 44544028, 16.873, 0), ((0, 1), (3, 1), (4, 1))),
((948 , 2481), (27671082, 44544028, 16.873, 0), ((3, 0), (5, 1), (0, 0))),
((948 , 2481), (27671082, 44544028, 16.873, 0), ((1, 1), (5, 0))),
((948 , 2481), (27671082, 44544028, 16.873, 0), ((1, 0), (4, 0))),
((2481, 2583), (44544028, 45330235, 0.786, 0), ((0, 1), (3, 1), (4, 1))),
((2481, 2583), (44544028, 45330235, 0.786, 0), ((3, 0), (5, 1), (0, 0))),
((2481, 2583), (44544028, 45330235, 0.786, 0), ((1, 0), (4, 0))),
((2583, 3107), (45330235, 49669743, 4.340, 0), ((0, 1), (3, 1), (4, 1), (5, 0))),
((2583, 3107), (45330235, 49669743, 4.340, 0), ((3, 0), (5, 1), (0, 0))),
((2583, 3107), (45330235, 49669743, 4.340, 0), ((1, 0), (4, 0))),
((3107, 3218), (49669743, 51156933, 1.487, 0), ((0, 1), (3, 1), (4, 1), (1, 1), (5, 0))),
((3107, 3218), (49669743, 51156933, 1.487, 0), ((3, 0), (5, 1), (0, 0))),
((3107, 3218), (49669743, 51156933, 1.487, 0), ((1, 0), (4, 0)))],
full_data=True, decimal=3, err_msg='Wrong IBD segments')
stats = np.array([(len(s.samples), s.length) for s in m])
best_segment = np.lexsort((-stats[:, 1], -stats[:, 0]))[0]
assert_equal(best_segment, 21, 'Wrong best segment (IBD set size + length)')
def test_phase_family(self):
'''Check phasing trivial cases in all genotyped trios.'''
problem = io.read_plink(pedigree=itu.HUTT_PED, prefix=itu.GENOTYPE_SAMPLE, haplotype=None)
itu.assert_size_equals(problem.genotype, 8, 1415)
assert_equal(len(problem.trios()), 869, 'Unexpected # of genotyped trios')
self.phaser.run(problem, PhaseParam(debug=False))
itu.assert_problem_stats(problem, 22640, 20225, 144)
def test_phase_trivial_cases(self):
'''Check phasing trivial cases in trios. The trio data is (0,1=parents, 2=child). The
solution is kept in the trio test file as the fictitious individual 3.'''
g = self.problem.genotype
itu.assert_size_equals(self.problem.genotype, 1, 2)
duo = (0, 1)
solution = self.solution.genotype.data
h = self.problem.haplotype
assert_problem_stats(self.problem, 4 * g.num_snps, 0, 0)
self.phaser.run(self.problem)
for snp in self.problem.snp_range:
expected_parent_genotype = solution[snp, duo[0], :]
#expected_child_genotype = solution[snp,trio[CHILD],:]
expected_child_haplotype = solution[snp, duo[1], :]
parent_genotype = g.data[snp, duo[0], :]
#child_genotype = g.data[snp,trio[CHILD]]
child_haplotype = h.data[snp, duo[1]]
'''
print 'SNP', snp
print 'Data', g.data[snp,trio,:]
print 'Imputed parent', parent_genotype
print 'Child hap', child_haplotype
print 'Solution hap', solution[snp,trio,:]
'''
assert_equal(child_haplotype, expected_child_haplotype, 'Wrong child haplotype by trivial phaser at snp %d' % (snp,))
assert_equal(parent_genotype, expected_parent_genotype, 'Wrong parent genotype imputation by trivial phaser at snp %d' % (snp,))
#assert_equal(np.sort(child_genotype), np.sort(expected_child_genotype), 'Wrong child genotype imputation by trivial phaser at snp %d' % (snp,))
assert_problem_stats(self.problem, 4 * g.num_snps, 4, 0)
def test_find_phased_sibs(self):
'''Test locating phased sibs of the unphased sample.'''
relatives = self.__phased_sibs(self.s)
assert_equal(relatives, [0, 1, 3, 4, 5], err_msg='Wrong phased sib set - IDs')
for sample in relatives:
self.assertTrue(self.problem.haplotype.fill_fraction(sample=sample) >= self.params.surrogate_parent_fill_threshold,
'Surrogate parent''s not phased enough')
def test_hash_rows(self):
'''Test hashing the rows of a numpy matrix.'''
a = np.array([[1, 2, 3], [4, 5, 6], [1, 2, 3], [7, 8, 9]], dtype=int)
d = dict(((Hashable(x), i) for (i, x) in enumerate(a)))
assert_equal(len(d), 3, 'Wrong hash table size')
# Hash value should be the last-encountered index of the corresponding row
assert_equal(d[Hashable(np.array([1, 2, 3]))], 2, 'Wrong hash table entry')
def test_trim(self):
"Tests trimming"
a = ma.arange(10)
assert_equal(mstats.trim(a), [0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
a = ma.arange(10)
assert_equal(mstats.trim(a, (2, 8)),
[None, None, 2, 3, 4, 5, 6, 7, 8, None])
a = ma.arange(10)
assert_equal(mstats.trim(a, limits=(2, 8), inclusive=(False, False)),
[None, None, None, 3, 4, 5, 6, 7, None, None])
a = ma.arange(10)
assert_equal(mstats.trim(a, limits=(0.1, 0.2), relative=True),
[None, 1, 2, 3, 4, 5, 6, 7, None, None])
#
a = ma.arange(12)
a[[0, -1]] = a[5] = masked
assert_equal(mstats.trim(a, (2, 8)),
[None, None, 2, 3, 4, None, 6, 7, 8, None, None, None])
#
x = ma.arange(100).reshape(10, 10)
trimx = mstats.trim(x, (0.1, 0.2), relative=True, axis=None)
assert_equal(trimx._mask.ravel(), [1] * 10 + [0] * 70 + [1] * 20)
trimx = mstats.trim(x, (0.1, 0.2), relative=True, axis=0)
assert_equal(trimx._mask.ravel(), [1] * 10 + [0] * 70 + [1] * 20)
trimx = mstats.trim(x, (0.1, 0.2), relative=True, axis=-1)
assert_equal(trimx._mask.T.ravel(), [1] * 10 + [0] * 70 + [1] * 20)
#
x = ma.arange(110).reshape(11, 10)
x[1] = masked
trimx = mstats.trim(x, (0.1, 0.2), relative=True, axis=None)
assert_equal(trimx._mask.ravel(), [1] * 20 + [0] * 70 + [1] * 20)
trimx = mstats.trim(x, (0.1, 0.2), relative=True, axis=0)
assert_equal(trimx._mask.ravel(), [1] * 20 + [0] * 70 + [1] * 20)
trimx = mstats.trim(x.T, (0.1, 0.2), relative=True, axis=-1)
assert_equal(trimx.T._mask.ravel(), [1] * 20 + [0] * 70 + [1] * 20)
def test_percentile(self):
x = np.arange(8) * 0.5
assert_equal(mstats.scoreatpercentile(x, 0), 0.)
assert_equal(mstats.scoreatpercentile(x, 100), 3.5)
assert_equal(mstats.scoreatpercentile(x, 50), 1.75)
def check_named_results(res, attributes, ma=False):
for i, attr in enumerate(attributes):
if ma:
ma_npt.assert_equal(res[i], getattr(res, attr))
else:
npt.assert_equal(res[i], getattr(res, attr))
def test_trim(self):
a = ma.arange(10)
assert_equal(mstats.trim(a), [0,1,2,3,4,5,6,7,8,9])
a = ma.arange(10)
assert_equal(mstats.trim(a,(2,8)), [None,None,2,3,4,5,6,7,8,None])
a = ma.arange(10)
assert_equal(mstats.trim(a,limits=(2,8),inclusive=(False,False)),
[None,None,None,3,4,5,6,7,None,None])
a = ma.arange(10)
assert_equal(mstats.trim(a,limits=(0.1,0.2),relative=True),
[None,1,2,3,4,5,6,7,None,None])
a = ma.arange(12)
a[[0,-1]] = a[5] = masked
assert_equal(mstats.trim(a, (2,8)),
[None, None, 2, 3, 4, None, 6, 7, 8, None, None, None])
x = ma.arange(100).reshape(10, 10)
expected = [1]*10 + [0]*70 + [1]*20
trimx = mstats.trim(x, (0.1,0.2), relative=True, axis=None)
assert_equal(trimx._mask.ravel(), expected)
trimx = mstats.trim(x, (0.1,0.2), relative=True, axis=0)
assert_equal(trimx._mask.ravel(), expected)
trimx = mstats.trim(x, (0.1,0.2), relative=True, axis=-1)
assert_equal(trimx._mask.T.ravel(), expected)
# same as above, but with an extra masked row inserted
x = ma.arange(110).reshape(11, 10)
x[1] = masked
expected = [1]*20 + [0]*70 + [1]*20
trimx = mstats.trim(x, (0.1,0.2), relative=True, axis=None)
assert_equal(trimx._mask.ravel(), expected)
trimx = mstats.trim(x, (0.1,0.2), relative=True, axis=0)
assert_equal(trimx._mask.ravel(), expected)
trimx = mstats.trim(x.T, (0.1,0.2), relative=True, axis=-1)
assert_equal(trimx.T._mask.ravel(), expected)
def test_ld_graph(self):
'''Test retrieving SNPs by chromosome.'''
chrom = 22
g = self.ld_dao.ld_graph(chrom)
assert_equal(g.number_of_nodes(), 2958,
'Wrong number of SNPs on chromosome %d' % (chrom, ))
def test_num_records(self):
'''Test getting the total # of SNP records.'''
assert_equal(self.ld_dao.num_ld_records(), 1394244,
'Wrong row count from SNP table')
assert_equal(self.ld_dao.num_snp_records(), 271486,
'Wrong row count from SNP table')
def test_subclasspreservation(self):
# Checks that masked_array(...,subok=True) preserves the class.
x = np.arange(5)
m = [0, 0, 1, 0, 0]
xinfo = [(i, j) for (i, j) in zip(x, m)]
xsub = MSubArray(x, mask=m, info={'xsub':xinfo})
#
mxsub = masked_array(xsub, subok=False)
self.assertTrue(not isinstance(mxsub, MSubArray))
self.assertTrue(isinstance(mxsub, MaskedArray))
assert_equal(mxsub._mask, m)
#
mxsub = asarray(xsub)
self.assertTrue(not isinstance(mxsub, MSubArray))
self.assertTrue(isinstance(mxsub, MaskedArray))
assert_equal(mxsub._mask, m)
#
mxsub = masked_array(xsub, subok=True)
self.assertTrue(isinstance(mxsub, MSubArray))
assert_equal(mxsub.info, xsub.info)
assert_equal(mxsub._mask, xsub._mask)
#
mxsub = asanyarray(xsub)
self.assertTrue(isinstance(mxsub, MSubArray))
assert_equal(mxsub.info, xsub.info)
assert_equal(mxsub._mask, m)
def test_masked_unary_operations(self):
# Tests masked_unary_operation
(x, mx) = self.data
with np.errstate(divide='ignore'):
self.assertTrue(isinstance(log(mx), mmatrix))
assert_equal(log(x), np.log(x))
def test_ediff1d_tobegin(self):
"Test ediff1d w/ to_begin"
x = masked_array(np.arange(5), mask=[1, 0, 0, 0, 1])
test = ediff1d(x, to_begin=masked)
control = array([0, 1, 1, 1, 4], mask=[1, 1, 0, 0, 1])
assert_equal(test, control)
assert_equal(test.data, control.data)
assert_equal(test.mask, control.mask)
#
test = ediff1d(x, to_begin=[1, 2, 3])
control = array([1, 2, 3, 1, 1, 1, 4], mask=[0, 0, 0, 1, 0, 0, 1])
assert_equal(test, control)
assert_equal(test.data, control.data)
assert_equal(test.mask, control.mask)
def assert_startswith(a, b):
# produces a better error message than assert_(a.startswith(b))
assert_equal(a[:len(b)], b)
def test_unique_onmaskedarray(self):
"Test unique on masked data w/use_mask=True"
data = masked_array([1, 1, 1, 2, 2, 3], mask=[0, 0, 1, 0, 1, 0])
test = unique(data, return_index=True, return_inverse=True)
assert_equal(test[0], masked_array([1, 2, 3, -1], mask=[0, 0, 0, 1]))
assert_equal(test[1], [0, 3, 5, 2])
assert_equal(test[2], [0, 0, 3, 1, 3, 2])
#
data.fill_value = 3
data = masked_array([1, 1, 1, 2, 2, 3],
mask=[0, 0, 1, 0, 1, 0],
fill_value=3)
test = unique(data, return_index=True, return_inverse=True)
assert_equal(test[0], masked_array([1, 2, 3, -1], mask=[0, 0, 0, 1]))
assert_equal(test[1], [0, 3, 5, 2])
assert_equal(test[2], [0, 0, 3, 1, 3, 2])
def test_ediff1d_tobegin_toend(self):
"Test ediff1d w/ to_begin and to_end"
x = masked_array(np.arange(5), mask=[1, 0, 0, 0, 1])
test = ediff1d(x, to_end=masked, to_begin=masked)
control = array([0, 1, 1, 1, 4, 0], mask=[1, 1, 0, 0, 1, 1])
assert_equal(test, control)
assert_equal(test.data, control.data)
assert_equal(test.mask, control.mask)
#
test = ediff1d(x, to_end=[1, 2, 3], to_begin=masked)
control = array([0, 1, 1, 1, 4, 1, 2, 3],
mask=[1, 1, 0, 0, 1, 0, 0, 0])
assert_equal(test, control)
assert_equal(test.data, control.data)
assert_equal(test.mask, control.mask)
def test_mask_rowcols(self):
"Tests mask_rowcols."
x = array(np.arange(9).reshape(3, 3),
mask=[[1, 0, 0], [0, 0, 0], [0, 0, 0]])
assert_equal(mask_rowcols(x).mask, [[1, 1, 1], [1, 0, 0], [1, 0, 0]])
assert_equal(
mask_rowcols(x, 0).mask, [[1, 1, 1], [0, 0, 0], [0, 0, 0]])
assert_equal(
mask_rowcols(x, 1).mask, [[1, 0, 0], [1, 0, 0], [1, 0, 0]])
x = array(x._data, mask=[[0, 0, 0], [0, 1, 0], [0, 0, 0]])
assert_equal(mask_rowcols(x).mask, [[0, 1, 0], [1, 1, 1], [0, 1, 0]])
assert_equal(
mask_rowcols(x, 0).mask, [[0, 0, 0], [1, 1, 1], [0, 0, 0]])
assert_equal(
mask_rowcols(x, 1).mask, [[0, 1, 0], [0, 1, 0], [0, 1, 0]])
x = array(x._data, mask=[[1, 0, 0], [0, 1, 0], [0, 0, 0]])
assert_equal(mask_rowcols(x).mask, [[1, 1, 1], [1, 1, 1], [1, 1, 0]])
assert_equal(
mask_rowcols(x, 0).mask, [[1, 1, 1], [1, 1, 1], [0, 0, 0]])
assert_equal(
mask_rowcols(
x,
1,
).mask, [[1, 1, 0], [1, 1, 0], [1, 1, 0]])
x = array(x._data, mask=[[1, 0, 0], [0, 1, 0], [0, 0, 1]])
self.assertTrue(mask_rowcols(x).all() is masked)
self.assertTrue(mask_rowcols(x, 0).all() is masked)
self.assertTrue(mask_rowcols(x, 1).all() is masked)
self.assertTrue(mask_rowcols(x).mask.all())
self.assertTrue(mask_rowcols(x, 0).mask.all())
self.assertTrue(mask_rowcols(x, 1).mask.all())
def test_unique_allmasked(self):
"Test all masked"
data = masked_array([1, 1, 1], mask=True)
test = unique(data, return_index=True, return_inverse=True)
assert_equal(test[0], masked_array([
1,
], mask=[True]))
assert_equal(test[1], [0])
assert_equal(test[2], [0, 0, 0])
#
"Test masked"
data = masked
test = unique(data, return_index=True, return_inverse=True)
assert_equal(test[0], masked_array(masked))
assert_equal(test[1], [0])
assert_equal(test[2], [0])
def test_contiguous(self):
"Tests notmasked_contiguous"
a = masked_array(np.arange(24).reshape(3, 8),
mask=[
[0, 0, 0, 0, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 0],
])
tmp = notmasked_contiguous(a, None)
assert_equal(tmp[-1], slice(23, 24, None))
assert_equal(tmp[-2], slice(16, 22, None))
assert_equal(tmp[-3], slice(0, 4, None))
#
tmp = notmasked_contiguous(a, 0)
self.assertTrue(len(tmp[-1]) == 1)
self.assertTrue(tmp[-2] is None)
assert_equal(tmp[-3], tmp[-1])
self.assertTrue(len(tmp[0]) == 2)
#
tmp = notmasked_contiguous(a, 1)
assert_equal(tmp[0][-1], slice(0, 4, None))
self.assertTrue(tmp[1] is None)
assert_equal(tmp[2][-1], slice(7, 8, None))
assert_equal(tmp[2][-2], slice(0, 6, None))
def test_dot(self):
"Tests dot product"
n = np.arange(1, 7)
#
m = [1, 0, 0, 0, 0, 0]
a = masked_array(n, mask=m).reshape(2, 3)
b = masked_array(n, mask=m).reshape(3, 2)
c = dot(a, b, True)
assert_equal(c.mask, [[1, 1], [1, 0]])
c = dot(b, a, True)
assert_equal(c.mask, [[1, 1, 1], [1, 0, 0], [1, 0, 0]])
c = dot(a, b, False)
assert_equal(c, np.dot(a.filled(0), b.filled(0)))
c = dot(b, a, False)
assert_equal(c, np.dot(b.filled(0), a.filled(0)))
#
m = [0, 0, 0, 0, 0, 1]
a = masked_array(n, mask=m).reshape(2, 3)
b = masked_array(n, mask=m).reshape(3, 2)
c = dot(a, b, True)
assert_equal(c.mask, [[0, 1], [1, 1]])
c = dot(b, a, True)
assert_equal(c.mask, [[0, 0, 1], [0, 0, 1], [1, 1, 1]])
c = dot(a, b, False)
assert_equal(c, np.dot(a.filled(0), b.filled(0)))
assert_equal(c, dot(a, b))
c = dot(b, a, False)
assert_equal(c, np.dot(b.filled(0), a.filled(0)))
#
m = [0, 0, 0, 0, 0, 0]
a = masked_array(n, mask=m).reshape(2, 3)
b = masked_array(n, mask=m).reshape(3, 2)
c = dot(a, b)
assert_equal(c.mask, nomask)
c = dot(b, a)
assert_equal(c.mask, nomask)
#
a = masked_array(n, mask=[1, 0, 0, 0, 0, 0]).reshape(2, 3)
b = masked_array(n, mask=[0, 0, 0, 0, 0, 0]).reshape(3, 2)
c = dot(a, b, True)
assert_equal(c.mask, [[1, 1], [0, 0]])
c = dot(a, b, False)
assert_equal(c, np.dot(a.filled(0), b.filled(0)))
c = dot(b, a, True)
assert_equal(c.mask, [[1, 0, 0], [1, 0, 0], [1, 0, 0]])
c = dot(b, a, False)
assert_equal(c, np.dot(b.filled(0), a.filled(0)))
#
a = masked_array(n, mask=[0, 0, 0, 0, 0, 1]).reshape(2, 3)
b = masked_array(n, mask=[0, 0, 0, 0, 0, 0]).reshape(3, 2)
c = dot(a, b, True)
assert_equal(c.mask, [[0, 0], [1, 1]])
c = dot(a, b)
assert_equal(c, np.dot(a.filled(0), b.filled(0)))
c = dot(b, a, True)
assert_equal(c.mask, [[0, 0, 1], [0, 0, 1], [0, 0, 1]])
c = dot(b, a, False)
assert_equal(c, np.dot(b.filled(0), a.filled(0)))
#
a = masked_array(n, mask=[0, 0, 0, 0, 0, 1]).reshape(2, 3)
b = masked_array(n, mask=[0, 0, 1, 0, 0, 0]).reshape(3, 2)
c = dot(a, b, True)
assert_equal(c.mask, [[1, 0], [1, 1]])
c = dot(a, b, False)
assert_equal(c, np.dot(a.filled(0), b.filled(0)))
c = dot(b, a, True)
assert_equal(c.mask, [[0, 0, 1], [1, 1, 1], [0, 0, 1]])
c = dot(b, a, False)
assert_equal(c, np.dot(b.filled(0), a.filled(0)))
def test_edges(self):
"Tests unmasked_edges"
data = masked_array(
np.arange(25).reshape(5, 5),
mask=[[0, 0, 1, 0, 0], [0, 0, 0, 1, 1], [1, 1, 0, 0, 0],
[0, 0, 0, 0, 0], [1, 1, 1, 0, 0]],
)
test = notmasked_edges(data, None)
assert_equal(test, [0, 24])
test = notmasked_edges(data, 0)
assert_equal(test[0], [(0, 0, 1, 0, 0), (0, 1, 2, 3, 4)])
assert_equal(test[1], [(3, 3, 3, 4, 4), (0, 1, 2, 3, 4)])
test = notmasked_edges(data, 1)
assert_equal(test[0], [(0, 1, 2, 3, 4), (0, 0, 2, 0, 3)])
assert_equal(test[1], [(0, 1, 2, 3, 4), (4, 2, 4, 4, 4)])
#
test = notmasked_edges(data.data, None)
assert_equal(test, [0, 24])
test = notmasked_edges(data.data, 0)
assert_equal(test[0], [(0, 0, 0, 0, 0), (0, 1, 2, 3, 4)])
assert_equal(test[1], [(4, 4, 4, 4, 4), (0, 1, 2, 3, 4)])
test = notmasked_edges(data.data, -1)
assert_equal(test[0], [(0, 1, 2, 3, 4), (0, 0, 0, 0, 0)])
assert_equal(test[1], [(0, 1, 2, 3, 4), (4, 4, 4, 4, 4)])
#
data[-2] = masked
test = notmasked_edges(data, 0)
assert_equal(test[0], [(0, 0, 1, 0, 0), (0, 1, 2, 3, 4)])
assert_equal(test[1], [(1, 1, 2, 4, 4), (0, 1, 2, 3, 4)])
test = notmasked_edges(data, -1)
assert_equal(test[0], [(0, 1, 2, 4), (0, 0, 2, 3)])
assert_equal(test[1], [(0, 1, 2, 4), (4, 2, 4, 4)])
def test_compress2d(self):
"Tests compress2d"
x = array(np.arange(9).reshape(3, 3),
mask=[[1, 0, 0], [0, 0, 0], [0, 0, 0]])
assert_equal(compress_rowcols(x), [[4, 5], [7, 8]])
assert_equal(compress_rowcols(x, 0), [[3, 4, 5], [6, 7, 8]])
assert_equal(compress_rowcols(x, 1), [[1, 2], [4, 5], [7, 8]])
x = array(x._data, mask=[[0, 0, 0], [0, 1, 0], [0, 0, 0]])
assert_equal(compress_rowcols(x), [[0, 2], [6, 8]])
assert_equal(compress_rowcols(x, 0), [[0, 1, 2], [6, 7, 8]])
assert_equal(compress_rowcols(x, 1), [[0, 2], [3, 5], [6, 8]])
x = array(x._data, mask=[[1, 0, 0], [0, 1, 0], [0, 0, 0]])
assert_equal(compress_rowcols(x), [[8]])
assert_equal(compress_rowcols(x, 0), [[6, 7, 8]])
assert_equal(compress_rowcols(
x,
1,
), [[2], [5], [8]])
x = array(x._data, mask=[[1, 0, 0], [0, 1, 0], [0, 0, 1]])
assert_equal(compress_rowcols(x).size, 0)
assert_equal(compress_rowcols(x, 0).size, 0)
assert_equal(compress_rowcols(x, 1).size, 0)
def test_testAverage3(self):
"Yet more tests of average!"
a = arange(6)
b = arange(6) * 3
r1, w1 = average([[a, b], [b, a]], axis=1, returned=1)
assert_equal(shape(r1), shape(w1))
assert_equal(r1.shape, w1.shape)
r2, w2 = average(ones((2, 2, 3)), axis=0, weights=[3, 1], returned=1)
assert_equal(shape(w2), shape(r2))
r2, w2 = average(ones((2, 2, 3)), returned=1)
assert_equal(shape(w2), shape(r2))
r2, w2 = average(ones((2, 2, 3)), weights=ones((2, 2, 3)), returned=1)
assert_equal(shape(w2), shape(r2))
a2d = array([[1, 2], [0, 4]], float)
a2dm = masked_array(a2d, [[False, False], [True, False]])
a2da = average(a2d, axis=0)
assert_equal(a2da, [0.5, 3.0])
a2dma = average(a2dm, axis=0)
assert_equal(a2dma, [1.0, 3.0])
a2dma = average(a2dm, axis=None)
assert_equal(a2dma, 7. / 3.)
a2dma = average(a2dm, axis=1)
assert_equal(a2dma, [1.5, 4.0])
def test_masked_all(self):
"Tests masked_all"
# Standard dtype
test = masked_all((2, ), dtype=float)
control = array([1, 1], mask=[1, 1], dtype=float)
assert_equal(test, control)
# Flexible dtype
dt = np.dtype({'names': ['a', 'b'], 'formats': ['f', 'f']})
test = masked_all((2, ), dtype=dt)
control = array([(0, 0), (0, 0)], mask=[(1, 1), (1, 1)], dtype=dt)
assert_equal(test, control)
test = masked_all((2, 2), dtype=dt)
control = array([[(0, 0), (0, 0)], [(0, 0), (0, 0)]],
mask=[[(1, 1), (1, 1)], [(1, 1), (1, 1)]],
dtype=dt)
assert_equal(test, control)
# Nested dtype
dt = np.dtype([('a', 'f'), ('b', [('ba', 'f'), ('bb', 'f')])])
test = masked_all((2, ), dtype=dt)
control = array([(1, (1, 1)), (1, (1, 1))],
mask=[(1, (1, 1)), (1, (1, 1))],
dtype=dt)
assert_equal(test, control)
test = masked_all((2, ), dtype=dt)
control = array([(1, (1, 1)), (1, (1, 1))],
mask=[(1, (1, 1)), (1, (1, 1))],
dtype=dt)
assert_equal(test, control)
test = masked_all((1, 1), dtype=dt)
control = array([[(1, (1, 1))]], mask=[[(1, (1, 1))]], dtype=dt)
assert_equal(test, control)
def test_testAverage1(self):
"Test of average."
ott = array([0., 1., 2., 3.], mask=[True, False, False, False])
assert_equal(2.0, average(ott, axis=0))
assert_equal(2.0, average(ott, weights=[1., 1., 2., 1.]))
result, wts = average(ott, weights=[1., 1., 2., 1.], returned=1)
assert_equal(2.0, result)
self.assertTrue(wts == 4.0)
ott[:] = masked
assert_equal(average(ott, axis=0).mask, [True])
ott = array([0., 1., 2., 3.], mask=[True, False, False, False])
ott = ott.reshape(2, 2)
ott[:, 1] = masked
assert_equal(average(ott, axis=0), [2.0, 0.0])
assert_equal(average(ott, axis=1).mask[0], [True])
assert_equal([2., 0.], average(ott, axis=0))
result, wts = average(ott, axis=0, returned=1)
assert_equal(wts, [1., 0.])
def test_onintegers_with_mask(self):
"Test average on integers with mask"
a = average(array([1, 2]))
assert_equal(a, 1.5)
a = average(array([1, 2, 3, 4], mask=[False, False, True, True]))
assert_equal(a, 1.5)
def test_zip_descr(self):
# Test zip_descr
(w, x, y, z) = self.data
# Std array
test = zip_descr((x, x), flatten=True)
assert_equal(test, np.dtype([('', int), ('', int)]))
test = zip_descr((x, x), flatten=False)
assert_equal(test, np.dtype([('', int), ('', int)]))
# Std & flexible-dtype
test = zip_descr((x, z), flatten=True)
assert_equal(test, np.dtype([('', int), ('A', '|S3'), ('B', float)]))
test = zip_descr((x, z), flatten=False)
assert_equal(test,
np.dtype([('', int), ('', [('A', '|S3'), ('B', float)])]))
# Standard & nested dtype
test = zip_descr((x, w), flatten=True)
assert_equal(
test, np.dtype([('', int), ('a', int), ('ba', float),
('bb', int)]))
test = zip_descr((x, w), flatten=False)
assert_equal(
test,
np.dtype([('', int),
('', [('a', int), ('b', [('ba', float),
('bb', int)])])]))
def test_testAverage2(self):
"More tests of average."
w1 = [0, 1, 1, 1, 1, 0]
w2 = [[0, 1, 1, 1, 1, 0], [1, 0, 0, 0, 0, 1]]
x = arange(6, dtype=np.float_)
assert_equal(average(x, axis=0), 2.5)
assert_equal(average(x, axis=0, weights=w1), 2.5)
y = array([arange(6, dtype=np.float_), 2.0 * arange(6)])
assert_equal(average(y, None), np.add.reduce(np.arange(6)) * 3. / 12.)
assert_equal(average(y, axis=0), np.arange(6) * 3. / 2.)
assert_equal(
average(y, axis=1),
[average(x, axis=0), average(x, axis=0) * 2.0])
assert_equal(average(y, None, weights=w2), 20. / 6.)
assert_equal(average(y, axis=0, weights=w2), [0., 1., 2., 3., 4., 10.])
assert_equal(
average(y, axis=1),
[average(x, axis=0), average(x, axis=0) * 2.0])
m1 = zeros(6)
m2 = [0, 0, 1, 1, 0, 0]
m3 = [[0, 0, 1, 1, 0, 0], [0, 1, 1, 1, 1, 0]]
m4 = ones(6)
m5 = [0, 1, 1, 1, 1, 1]
assert_equal(average(masked_array(x, m1), axis=0), 2.5)
assert_equal(average(masked_array(x, m2), axis=0), 2.5)
assert_equal(average(masked_array(x, m4), axis=0).mask, [True])
assert_equal(average(masked_array(x, m5), axis=0), 0.0)
assert_equal(count(average(masked_array(x, m4), axis=0)), 0)
z = masked_array(y, m3)
assert_equal(average(z, None), 20. / 6.)
assert_equal(average(z, axis=0), [0., 1., 99., 99., 4.0, 7.5])
assert_equal(average(z, axis=1), [2.5, 5.0])
assert_equal(average(z, axis=0, weights=w2),
[0., 1., 99., 99., 4.0, 10.0])
def test_structured_to_unstructured(self):
a = np.zeros(4, dtype=[('a', 'i4'), ('b', 'f4,u2'), ('c', 'f4', 2)])
out = structured_to_unstructured(a)
assert_equal(out, np.zeros((4, 5), dtype='f8'))
b = np.array([(1, 2, 5), (4, 5, 7), (7, 8, 11), (10, 11, 12)],
dtype=[('x', 'i4'), ('y', 'f4'), ('z', 'f8')])
out = np.mean(structured_to_unstructured(b[['x', 'z']]), axis=-1)
assert_equal(out, np.array([3., 5.5, 9., 11.]))
out = np.mean(structured_to_unstructured(b[['x']]), axis=-1)
assert_equal(out, np.array([1., 4., 7., 10.]))
c = np.arange(20).reshape((4, 5))
out = unstructured_to_structured(c, a.dtype)
want = np.array([(0, (1., 2), [3., 4.]), (5, (6., 7), [8., 9.]),
(10, (11., 12), [13., 14.]),
(15, (16., 17), [18., 19.])],
dtype=[('a', 'i4'), ('b', [('f0', 'f4'),
('f1', 'u2')]),
('c', 'f4', (2, ))])
assert_equal(out, want)
d = np.array([(1, 2, 5), (4, 5, 7), (7, 8, 11), (10, 11, 12)],
dtype=[('x', 'i4'), ('y', 'f4'), ('z', 'f8')])
assert_equal(apply_along_fields(np.mean, d),
np.array([8.0 / 3, 16.0 / 3, 26.0 / 3, 11.]))
assert_equal(apply_along_fields(np.mean, d[['x', 'z']]),
np.array([3., 5.5, 9., 11.]))
# check that for uniform field dtypes we get a view, not a copy:
d = np.array([(1, 2, 5), (4, 5, 7), (7, 8, 11), (10, 11, 12)],
dtype=[('x', 'i4'), ('y', 'i4'), ('z', 'i4')])
dd = structured_to_unstructured(d)
ddd = unstructured_to_structured(dd, d.dtype)
assert_(dd.base is d)
assert_(ddd.base is d)
# including uniform fields with subarrays unpacked
d = np.array([(1, [2, 3], [[4, 5], [6, 7]]),
(8, [9, 10], [[11, 12], [13, 14]])],
dtype=[('x0', 'i4'), ('x1', ('i4', 2)),
('x2', ('i4', (2, 2)))])
dd = structured_to_unstructured(d)
ddd = unstructured_to_structured(dd, d.dtype)
assert_(dd.base is d)
assert_(ddd.base is d)
# test that nested fields with identical names don't break anything
point = np.dtype([('x', int), ('y', int)])
triangle = np.dtype([('a', point), ('b', point), ('c', point)])
arr = np.zeros(10, triangle)
res = structured_to_unstructured(arr, dtype=int)
assert_equal(res, np.zeros((10, 6), dtype=int))
# test nested combinations of subarrays and structured arrays, gh-13333
def subarray(dt, shape):
return np.dtype((dt, shape))
def structured(*dts):
return np.dtype([('x{}'.format(i), dt)
for i, dt in enumerate(dts)])
def inspect(dt, dtype=None):
arr = np.zeros((), dt)
ret = structured_to_unstructured(arr, dtype=dtype)
backarr = unstructured_to_structured(ret, dt)
return ret.shape, ret.dtype, backarr.dtype
dt = structured(subarray(structured(np.int32, np.int32), 3))
assert_equal(inspect(dt), ((6, ), np.int32, dt))
dt = structured(subarray(subarray(np.int32, 2), 2))
assert_equal(inspect(dt), ((4, ), np.int32, dt))
dt = structured(np.int32)
assert_equal(inspect(dt), ((1, ), np.int32, dt))
dt = structured(np.int32, subarray(subarray(np.int32, 2), 2))
assert_equal(inspect(dt), ((5, ), np.int32, dt))
dt = structured()
assert_raises(ValueError, structured_to_unstructured, np.zeros(3, dt))
# these currently don't work, but we may make it work in the future
assert_raises(NotImplementedError,
structured_to_unstructured,
np.zeros(3, dt),
dtype=np.int32)
assert_raises(NotImplementedError, unstructured_to_structured,
np.zeros((3, 0), dtype=np.int32))
def test_3d(self):
a = arange(12.).reshape(2, 2, 3)
def myfunc(b):
return b[1]
xa = apply_along_axis(myfunc, 2, a)
assert_equal(xa, [[1, 4], [7, 10]])
def test_mode(self):
a1 = [0,0,0,1,1,1,2,3,3,3,3,4,5,6,7]
a2 = np.reshape(a1, (3,5))
a3 = np.array([1,2,3,4,5,6])
a4 = np.reshape(a3, (3,2))
ma1 = ma.masked_where(ma.array(a1) > 2, a1)
ma2 = ma.masked_where(a2 > 2, a2)
ma3 = ma.masked_where(a3 < 2, a3)
ma4 = ma.masked_where(ma.array(a4) < 2, a4)
assert_equal(mstats.mode(a1, axis=None), (3,4))
assert_equal(mstats.mode(a1, axis=0), (3,4))
assert_equal(mstats.mode(ma1, axis=None), (0,3))
assert_equal(mstats.mode(a2, axis=None), (3,4))
assert_equal(mstats.mode(ma2, axis=None), (0,3))
assert_equal(mstats.mode(a3, axis=None), (1,1))
assert_equal(mstats.mode(ma3, axis=None), (2,1))
assert_equal(mstats.mode(a2, axis=0), ([[0,0,0,1,1]], [[1,1,1,1,1]]))
assert_equal(mstats.mode(ma2, axis=0), ([[0,0,0,1,1]], [[1,1,1,1,1]]))
assert_equal(mstats.mode(a2, axis=-1), ([[0],[3],[3]], [[3],[3],[1]]))
assert_equal(mstats.mode(ma2, axis=-1), ([[0],[1],[0]], [[3],[1],[0]]))
assert_equal(mstats.mode(ma4, axis=0), ([[3,2]], [[1,1]]))
assert_equal(mstats.mode(ma4, axis=-1), ([[2],[3],[5]], [[1],[1],[1]]))
a1_res = mstats.mode(a1, axis=None)
# test for namedtuple attributes
attributes = ('mode', 'count')
check_named_results(a1_res, attributes, ma=True)
def test_field_assignment_by_name(self):
a = np.ones(2, dtype=[('a', 'i4'), ('b', 'f8'), ('c', 'u1')])
newdt = [('b', 'f4'), ('c', 'u1')]
assert_equal(require_fields(a, newdt), np.ones(2, newdt))
b = np.array([(1, 2), (3, 4)], dtype=newdt)
assign_fields_by_name(a, b, zero_unassigned=False)
assert_equal(a, np.array([(1, 1, 2), (1, 3, 4)], dtype=a.dtype))
assign_fields_by_name(a, b)
assert_equal(a, np.array([(0, 1, 2), (0, 3, 4)], dtype=a.dtype))
# test nested fields
a = np.ones(2, dtype=[('a', [('b', 'f8'), ('c', 'u1')])])
newdt = [('a', [('c', 'u1')])]
assert_equal(require_fields(a, newdt), np.ones(2, newdt))
b = np.array([((2, ), ), ((3, ), )], dtype=newdt)
assign_fields_by_name(a, b, zero_unassigned=False)
assert_equal(a, np.array([((1, 2), ), ((1, 3), )], dtype=a.dtype))
assign_fields_by_name(a, b)
assert_equal(a, np.array([((0, 2), ), ((0, 3), )], dtype=a.dtype))
# test unstructured code path for 0d arrays
a, b = np.array(3), np.array(0)
assign_fields_by_name(b, a)
assert_equal(b[()], 3)
def test_trim_old(self):
x = ma.arange(100)
assert_equal(mstats.trimboth(x).count(), 60)
assert_equal(mstats.trimtail(x,tail='r').count(), 80)
x[50:70] = masked
trimx = mstats.trimboth(x)
assert_equal(trimx.count(), 48)
assert_equal(trimx._mask, [1]*16 + [0]*34 + [1]*20 + [0]*14 + [1]*16)
x._mask = nomask
x.shape = (10,10)
assert_equal(mstats.trimboth(x).count(), 60)
assert_equal(mstats.trimtail(x).count(), 80)
def test_find_duplicates(self):
# Test find_duplicates
a = ma.array([(2, (2., 'B')), (1, (2., 'B')), (2, (2., 'B')),
(1, (1., 'B')), (2, (2., 'B')), (2, (2., 'C'))],
mask=[(0, (0, 0)), (0, (0, 0)), (0, (0, 0)), (0, (0, 0)),
(1, (0, 0)), (0, (1, 0))],
dtype=[('A', int), ('B', [('BA', float), ('BB', '|S1')])])
test = find_duplicates(a, ignoremask=False, return_index=True)
control = [0, 2]
assert_equal(sorted(test[-1]), control)
assert_equal(test[0], a[test[-1]])
test = find_duplicates(a, key='A', return_index=True)
control = [0, 1, 2, 3, 5]
assert_equal(sorted(test[-1]), control)
assert_equal(test[0], a[test[-1]])
test = find_duplicates(a, key='B', return_index=True)
control = [0, 1, 2, 4]
assert_equal(sorted(test[-1]), control)
assert_equal(test[0], a[test[-1]])
test = find_duplicates(a, key='BA', return_index=True)
control = [0, 1, 2, 4]
assert_equal(sorted(test[-1]), control)
assert_equal(test[0], a[test[-1]])
test = find_duplicates(a, key='BB', return_index=True)
control = [0, 1, 2, 3, 4]
assert_equal(sorted(test[-1]), control)
assert_equal(test[0], a[test[-1]])
